File size: 19,608 Bytes
9aa5185 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 | #!/usr/bin/env python3
"""
Session Search Tool - Long-Term Conversation Recall
Searches past session transcripts in SQLite via FTS5, then summarizes the top
matching sessions using a cheap/fast model (same pattern as web_extract).
Returns focused summaries of past conversations rather than raw transcripts,
keeping the main model's context window clean.
Flow:
1. FTS5 search finds matching messages ranked by relevance
2. Groups by session, takes the top N unique sessions (default 3)
3. Loads each session's conversation, truncates to ~100k chars centered on matches
4. Sends to Gemini Flash with a focused summarization prompt
5. Returns per-session summaries with metadata
"""
import asyncio
import concurrent.futures
import json
import os
import logging
from typing import Dict, Any, List, Optional, Union
from agent.auxiliary_client import async_call_llm
MAX_SESSION_CHARS = 100_000
MAX_SUMMARY_TOKENS = 10000
def _format_timestamp(ts: Union[int, float, str, None]) -> str:
"""Convert a Unix timestamp (float/int) or ISO string to a human-readable date.
Returns "unknown" for None, str(ts) if conversion fails.
"""
if ts is None:
return "unknown"
try:
if isinstance(ts, (int, float)):
from datetime import datetime
dt = datetime.fromtimestamp(ts)
return dt.strftime("%B %d, %Y at %I:%M %p")
if isinstance(ts, str):
if ts.replace(".", "").replace("-", "").isdigit():
from datetime import datetime
dt = datetime.fromtimestamp(float(ts))
return dt.strftime("%B %d, %Y at %I:%M %p")
return ts
except (ValueError, OSError, OverflowError) as e:
# Log specific errors for debugging while gracefully handling edge cases
logging.debug("Failed to format timestamp %s: %s", ts, e, exc_info=True)
except Exception as e:
logging.debug("Unexpected error formatting timestamp %s: %s", ts, e, exc_info=True)
return str(ts)
def _format_conversation(messages: List[Dict[str, Any]]) -> str:
"""Format session messages into a readable transcript for summarization."""
parts = []
for msg in messages:
role = msg.get("role", "unknown").upper()
content = msg.get("content") or ""
tool_name = msg.get("tool_name")
if role == "TOOL" and tool_name:
# Truncate long tool outputs
if len(content) > 500:
content = content[:250] + "\n...[truncated]...\n" + content[-250:]
parts.append(f"[TOOL:{tool_name}]: {content}")
elif role == "ASSISTANT":
# Include tool call names if present
tool_calls = msg.get("tool_calls")
if tool_calls and isinstance(tool_calls, list):
tc_names = []
for tc in tool_calls:
if isinstance(tc, dict):
name = tc.get("name") or tc.get("function", {}).get("name", "?")
tc_names.append(name)
if tc_names:
parts.append(f"[ASSISTANT]: [Called: {', '.join(tc_names)}]")
if content:
parts.append(f"[ASSISTANT]: {content}")
else:
parts.append(f"[ASSISTANT]: {content}")
else:
parts.append(f"[{role}]: {content}")
return "\n\n".join(parts)
def _truncate_around_matches(
full_text: str, query: str, max_chars: int = MAX_SESSION_CHARS
) -> str:
"""
Truncate a conversation transcript to max_chars, centered around
where the query terms appear. Keeps content near matches, trims the edges.
"""
if len(full_text) <= max_chars:
return full_text
# Find the first occurrence of any query term
query_terms = query.lower().split()
text_lower = full_text.lower()
first_match = len(full_text)
for term in query_terms:
pos = text_lower.find(term)
if pos != -1 and pos < first_match:
first_match = pos
if first_match == len(full_text):
# No match found, take from the start
first_match = 0
# Center the window around the first match
half = max_chars // 2
start = max(0, first_match - half)
end = min(len(full_text), start + max_chars)
if end - start < max_chars:
start = max(0, end - max_chars)
truncated = full_text[start:end]
prefix = "...[earlier conversation truncated]...\n\n" if start > 0 else ""
suffix = "\n\n...[later conversation truncated]..." if end < len(full_text) else ""
return prefix + truncated + suffix
async def _summarize_session(
conversation_text: str, query: str, session_meta: Dict[str, Any]
) -> Optional[str]:
"""Summarize a single session conversation focused on the search query."""
system_prompt = (
"You are reviewing a past conversation transcript to help recall what happened. "
"Summarize the conversation with a focus on the search topic. Include:\n"
"1. What the user asked about or wanted to accomplish\n"
"2. What actions were taken and what the outcomes were\n"
"3. Key decisions, solutions found, or conclusions reached\n"
"4. Any specific commands, files, URLs, or technical details that were important\n"
"5. Anything left unresolved or notable\n\n"
"Be thorough but concise. Preserve specific details (commands, paths, error messages) "
"that would be useful to recall. Write in past tense as a factual recap."
)
source = session_meta.get("source", "unknown")
started = _format_timestamp(session_meta.get("started_at"))
user_prompt = (
f"Search topic: {query}\n"
f"Session source: {source}\n"
f"Session date: {started}\n\n"
f"CONVERSATION TRANSCRIPT:\n{conversation_text}\n\n"
f"Summarize this conversation with focus on: {query}"
)
max_retries = 3
for attempt in range(max_retries):
try:
response = await async_call_llm(
task="session_search",
messages=[
{"role": "system", "content": system_prompt},
{"role": "user", "content": user_prompt},
],
temperature=0.1,
max_tokens=MAX_SUMMARY_TOKENS,
)
return response.choices[0].message.content.strip()
except RuntimeError:
logging.warning("No auxiliary model available for session summarization")
return None
except Exception as e:
if attempt < max_retries - 1:
await asyncio.sleep(1 * (attempt + 1))
else:
logging.warning(
"Session summarization failed after %d attempts: %s",
max_retries,
e,
exc_info=True,
)
return None
def _list_recent_sessions(db, limit: int, current_session_id: str = None) -> str:
"""Return metadata for the most recent sessions (no LLM calls)."""
try:
sessions = db.list_sessions_rich(limit=limit + 5) # fetch extra to skip current
# Resolve current session lineage to exclude it
current_root = None
if current_session_id:
try:
sid = current_session_id
visited = set()
while sid and sid not in visited:
visited.add(sid)
s = db.get_session(sid)
parent = s.get("parent_session_id") if s else None
sid = parent if parent else None
current_root = max(visited, key=len) if visited else current_session_id
except Exception:
current_root = current_session_id
results = []
for s in sessions:
sid = s.get("id", "")
if current_root and (sid == current_root or sid == current_session_id):
continue
# Skip child/delegation sessions (they have parent_session_id)
if s.get("parent_session_id"):
continue
results.append({
"session_id": sid,
"title": s.get("title") or None,
"source": s.get("source", ""),
"started_at": s.get("started_at", ""),
"last_active": s.get("last_active", ""),
"message_count": s.get("message_count", 0),
"preview": s.get("preview", ""),
})
if len(results) >= limit:
break
return json.dumps({
"success": True,
"mode": "recent",
"results": results,
"count": len(results),
"message": f"Showing {len(results)} most recent sessions. Use a keyword query to search specific topics.",
}, ensure_ascii=False)
except Exception as e:
logging.error("Error listing recent sessions: %s", e, exc_info=True)
return json.dumps({"success": False, "error": f"Failed to list recent sessions: {e}"}, ensure_ascii=False)
def session_search(
query: str,
role_filter: str = None,
limit: int = 3,
db=None,
current_session_id: str = None,
) -> str:
"""
Search past sessions and return focused summaries of matching conversations.
Uses FTS5 to find matches, then summarizes the top sessions with Gemini Flash.
The current session is excluded from results since the agent already has that context.
"""
if db is None:
return json.dumps({"success": False, "error": "Session database not available."}, ensure_ascii=False)
limit = min(limit, 5) # Cap at 5 sessions to avoid excessive LLM calls
# Recent sessions mode: when query is empty, return metadata for recent sessions.
# No LLM calls — just DB queries for titles, previews, timestamps.
if not query or not query.strip():
return _list_recent_sessions(db, limit, current_session_id)
query = query.strip()
try:
# Parse role filter
role_list = None
if role_filter and role_filter.strip():
role_list = [r.strip() for r in role_filter.split(",") if r.strip()]
# FTS5 search -- get matches ranked by relevance
raw_results = db.search_messages(
query=query,
role_filter=role_list,
limit=50, # Get more matches to find unique sessions
offset=0,
)
if not raw_results:
return json.dumps({
"success": True,
"query": query,
"results": [],
"count": 0,
"message": "No matching sessions found.",
}, ensure_ascii=False)
# Resolve child sessions to their parent — delegation stores detailed
# content in child sessions, but the user's conversation is the parent.
def _resolve_to_parent(session_id: str) -> str:
"""Walk delegation chain to find the root parent session ID."""
visited = set()
sid = session_id
while sid and sid not in visited:
visited.add(sid)
try:
session = db.get_session(sid)
if not session:
break
parent = session.get("parent_session_id")
if parent:
sid = parent
else:
break
except Exception as e:
logging.debug(
"Error resolving parent for session %s: %s",
sid,
e,
exc_info=True,
)
break
return sid
current_lineage_root = (
_resolve_to_parent(current_session_id) if current_session_id else None
)
# Group by resolved (parent) session_id, dedup, skip the current
# session lineage. Compression and delegation create child sessions
# that still belong to the same active conversation.
seen_sessions = {}
for result in raw_results:
raw_sid = result["session_id"]
resolved_sid = _resolve_to_parent(raw_sid)
# Skip the current session lineage — the agent already has that
# context, even if older turns live in parent fragments.
if current_lineage_root and resolved_sid == current_lineage_root:
continue
if current_session_id and raw_sid == current_session_id:
continue
if resolved_sid not in seen_sessions:
result = dict(result)
result["session_id"] = resolved_sid
seen_sessions[resolved_sid] = result
if len(seen_sessions) >= limit:
break
# Prepare all sessions for parallel summarization
tasks = []
for session_id, match_info in seen_sessions.items():
try:
messages = db.get_messages_as_conversation(session_id)
if not messages:
continue
session_meta = db.get_session(session_id) or {}
conversation_text = _format_conversation(messages)
conversation_text = _truncate_around_matches(conversation_text, query)
tasks.append((session_id, match_info, conversation_text, session_meta))
except Exception as e:
logging.warning(
"Failed to prepare session %s: %s",
session_id,
e,
exc_info=True,
)
# Summarize all sessions in parallel
async def _summarize_all() -> List[Union[str, Exception]]:
"""Summarize all sessions in parallel."""
coros = [
_summarize_session(text, query, meta)
for _, _, text, meta in tasks
]
return await asyncio.gather(*coros, return_exceptions=True)
try:
asyncio.get_running_loop()
with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
results = pool.submit(lambda: asyncio.run(_summarize_all())).result(timeout=60)
except RuntimeError:
# No event loop running, create a new one
results = asyncio.run(_summarize_all())
except concurrent.futures.TimeoutError:
logging.warning(
"Session summarization timed out after 60 seconds",
exc_info=True,
)
return json.dumps({
"success": False,
"error": "Session summarization timed out. Try a more specific query or reduce the limit.",
}, ensure_ascii=False)
summaries = []
for (session_id, match_info, _, _), result in zip(tasks, results):
if isinstance(result, Exception):
logging.warning(
"Failed to summarize session %s: %s",
session_id,
result,
exc_info=True,
)
continue
if result:
summaries.append({
"session_id": session_id,
"when": _format_timestamp(match_info.get("session_started")),
"source": match_info.get("source", "unknown"),
"model": match_info.get("model"),
"summary": result,
})
return json.dumps({
"success": True,
"query": query,
"results": summaries,
"count": len(summaries),
"sessions_searched": len(seen_sessions),
}, ensure_ascii=False)
except Exception as e:
logging.error("Session search failed: %s", e, exc_info=True)
return json.dumps({"success": False, "error": f"Search failed: {str(e)}"}, ensure_ascii=False)
def check_session_search_requirements() -> bool:
"""Requires SQLite state database and an auxiliary text model."""
try:
from hermes_state import DEFAULT_DB_PATH
return DEFAULT_DB_PATH.parent.exists()
except ImportError:
return False
SESSION_SEARCH_SCHEMA = {
"name": "session_search",
"description": (
"Search your long-term memory of past conversations, or browse recent sessions. This is your recall -- "
"every past session is searchable, and this tool summarizes what happened.\n\n"
"TWO MODES:\n"
"1. Recent sessions (no query): Call with no arguments to see what was worked on recently. "
"Returns titles, previews, and timestamps. Zero LLM cost, instant. "
"Start here when the user asks what were we working on or what did we do recently.\n"
"2. Keyword search (with query): Search for specific topics across all past sessions. "
"Returns LLM-generated summaries of matching sessions.\n\n"
"USE THIS PROACTIVELY when:\n"
"- The user says 'we did this before', 'remember when', 'last time', 'as I mentioned'\n"
"- The user asks about a topic you worked on before but don't have in current context\n"
"- The user references a project, person, or concept that seems familiar but isn't in memory\n"
"- You want to check if you've solved a similar problem before\n"
"- The user asks 'what did we do about X?' or 'how did we fix Y?'\n\n"
"Don't hesitate to search when it is actually cross-session -- it's fast and cheap. "
"Better to search and confirm than to guess or ask the user to repeat themselves.\n\n"
"Search syntax: keywords joined with OR for broad recall (elevenlabs OR baseten OR funding), "
"phrases for exact match (\"docker networking\"), boolean (python NOT java), prefix (deploy*). "
"IMPORTANT: Use OR between keywords for best results — FTS5 defaults to AND which misses "
"sessions that only mention some terms. If a broad OR query returns nothing, try individual "
"keyword searches in parallel. Returns summaries of the top matching sessions."
),
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query — keywords, phrases, or boolean expressions to find in past sessions. Omit this parameter entirely to browse recent sessions instead (returns titles, previews, timestamps with no LLM cost).",
},
"role_filter": {
"type": "string",
"description": "Optional: only search messages from specific roles (comma-separated). E.g. 'user,assistant' to skip tool outputs.",
},
"limit": {
"type": "integer",
"description": "Max sessions to summarize (default: 3, max: 5).",
"default": 3,
},
},
"required": [],
},
}
# --- Registry ---
from tools.registry import registry
registry.register(
name="session_search",
toolset="session_search",
schema=SESSION_SEARCH_SCHEMA,
handler=lambda args, **kw: session_search(
query=args.get("query") or "",
role_filter=args.get("role_filter"),
limit=args.get("limit", 3),
db=kw.get("db"),
current_session_id=kw.get("current_session_id")),
check_fn=check_session_search_requirements,
emoji="🔍",
)
|